Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    specific nouns and phrases that signal legal permissions or indications of rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abis
    -0.17
    iais
    -0.16
    oki
    -0.15
    (savedInstanceState
    -0.15
     Pax
    -0.14
    é¬
    -0.14
    éĥ
    -0.14
    celik
    -0.14
    _proxy
    -0.14
    é«
    -0.14
    POSITIVE LOGITS
     Gill
    0.15
    ieran
    0.15
    enko
    0.14
     area
    0.14
     extr
    0.14
    uren
    0.13
     Provincial
    0.13
    obra
    0.13
     Urb
    0.13
     Humb
    0.13
    Act Density 0.003%

    No Known Activations